
Recent Posts
Recent Comments
Yas on Kernels Sarnath on Kernels Artificial Intellige… on GPUs and Neural Networks Artificial Intellige… on GPUs and Neural Networks Artificial Intellige… on GPUs and Neural Networks Archives
 December 2016
 November 2016
 October 2016
 June 2016
 April 2016
 January 2016
 November 2015
 October 2015
 July 2015
 June 2015
 May 2015
 January 2015
 September 2014
 June 2014
 May 2014
 March 2014
 February 2014
 January 2014
 December 2013
 October 2013
 September 2013
 August 2013
 July 2013
 June 2013
 May 2013
 April 2013
 March 2013
Categories
Meta
Category Archives: Uncategorized
Goals of Interpretability
In my last post, I looked at the gap that arises when we delegate parts of our thought processes to algorithmic models, rather than incorporating the rules they identify directly into our mental models, like we do with traditional statistics. I … Continue reading
Posted in Interpretability, Uncategorized
1 Comment
Rolling and Unrolling RNNs
A while back, I discussed Recurrent Neural Networks (RNNs), a type of artificial neural network in which some of the connections between neurons point “backwards”. When a sequence of inputs is fed into such a network, the backward arrows feed … Continue reading
Posted in Uncategorized
2 Comments
Duality and Coclustering
In mathematics, the term “duality” usually refers to a relationship between two object, or types of objects, that is somehow symmetric. (Note that this is different from some other uses of the term outside of mathematics.) For example, if we … Continue reading
Posted in Uncategorized
4 Comments
TILO/PRC Clustering
In the last few weeks, we’ve looked at a number of different algorithms for dividing a data set into clusters, and a few ways of measuring how good the clusters found by such an algorithm are. This week, I’m going … Continue reading
Posted in Uncategorized
Leave a comment
Graphs and networks
In last week’s post, I discussed the difference between the extrinsic and intrinsic structures of a data set. The extrinsic structure, which has to do with how the data points sit in the data space, is encoded by the vector … Continue reading
Posted in Uncategorized
2 Comments